Self-Correcting Generalization

Abstract

A system is described which creates and generalizes rules from examples. The system can recover from an initially misleading input sequence by keeping evidence which supports (or doesn't support) a given generalization. By undoing over-generalizations, the system maintains a minimal set of rules for a given set of inputs.

Cite

Text

Whitehill. "Self-Correcting Generalization." AAAI Conference on Artificial Intelligence, 1980.

Markdown

[Whitehill. "Self-Correcting Generalization." AAAI Conference on Artificial Intelligence, 1980.](https://mlanthology.org/aaai/1980/whitehill1980aaai-self/)

BibTeX

@inproceedings{whitehill1980aaai-self,
  title     = {{Self-Correcting Generalization}},
  author    = {Whitehill, Stephen B.},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {1980},
  pages     = {240-242},
  url       = {https://mlanthology.org/aaai/1980/whitehill1980aaai-self/}
}